How to Use the Honeycomb MCP in Pydantic AI

Q: How do I hook up Honeycomb to Pydantic AI?

Run pip install "pydantic-ai-slimmcp". Initialize an MCPToolset with your HTTP endpoint and pass it to your Agent. Drop the deprecated MCPServerHTTP class.

Q: How do I list available Honeycomb datasets in Pydantic AI?

Your agent calls the MCP listdatasets tool. It returns an array of dataset objects containing the slugs required for other tool operations.

Force strict runtime validation on your Honeycomb observability data with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Honeycomb MCP to Pydantic AI

Create your Vinkius account to connect Honeycomb to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Honeycomb with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe telemetry via the MCP Server

Observability APIs return massive, deeply nested JSON objects. Your agent calls `get_dataset_details` and `list_dataset_columns` to pull schema data. Pydantic AI validates every single field against your defined models before the agent even sees it. If the API changes or returns a weird type, the system fails loudly. You never have to worry about silent corruption ruining your automated triage. The agent only acts on data that matches your exact specifications.

Build deterministic query specifications

Hallucinated query structures will break your automated runbooks. The agent uses `create_query_specification` to generate the exact JSON required for execution. It passes that validated spec to `run_query` to get a result ID. Retrieving the data requires hitting `get_query_result`. Because you enforce strict typing, the resulting time-series data maps perfectly into your internal data structures. You get reliable, predictable outputs every single time.

Manage markers and triggers safely

Dropping annotations on a timeline requires precision. Your agent formats the exact `body_json` payload needed for `create_marker`. It can target specific datasets or use the global flag for team-wide deployments. Reading existing state is just as strict. The agent pulls active configurations using `list_triggers` and `list_markers`. It cross-references those alerts against your team details fetched via `get_team_details`.

Setup guide

Set up Honeycomb MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "honeycomb-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Honeycomb tools.",
)

result = await agent.run("List recent Honeycomb transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Honeycomb. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Honeycomb now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Honeycomb MCP in Pydantic AI

Run `pip install "pydantic-ai-slim[mcp]"`. Initialize an `MCPToolset` with your HTTP endpoint and pass it to your Agent. Drop the deprecated `MCPServerHTTP` class.

The framework validates the structure of the JSON passed to `create_query_specification`. It cannot validate if the query itself makes logical sense for your specific dataset.

Your agent calls the MCP `list_datasets` tool. It returns an array of dataset objects containing the slugs required for other tool operations.

Yes. Pydantic AI is completely model-agnostic. You can pipe the outputs from `list_honeycomb_boards` or `list_queries` into any LLM you choose.

Time-series aggregates and span data flow through a secure, ephemeral V8 isolate on Vinkius. The framework strictly parses this payload locally, ensuring no rogue data escapes your defined schemas.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript